© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71063
    Prev
    Next
    INDEX
    Explanations

    command line options or arguments

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on placeholder tokens in usage/syntax lines—i.e. bracketed ([…] ) or angle-bracketed (<…>) command-line argument names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.75
     those
    -1.30
     the
    -1.26
     these
    -1.11
     overall
    -1.09
     our
    -1.09
    хии
    -1.06
    一旁的
    -1.02
     aforementioned
    -1.00
    ceğim
    -0.99
    POSITIVE LOGITS
     or
    1.47
     optionally
    1.26
    ='';
    1.17
     anledning
    1.17
     améli
    1.17
    OOTDTY
    1.15
    optional
    1.14
    蝼
    1.13
     beſ
    1.13
    íny
    1.10
    Activations Density 0.019%

    No Known Activations